All I can do is shake my head. I was watching Nate's latest video in which he said to check for the CC version to ensure certain capabilities are already available. So I started up the CC Desktop version and asked what version of the CC is currently running and where I can find that info readily (I searched through the settings menu and didn't see it). It responded with: I'll check the version right now. Ran Check Claude Code version You're on Claude Code version 2.1.114. Where to see this: - Terminal: Run claude --version anytime - In-session: Type /status while in a Claude Code session — shows version along with model, context usage, and other info - VS Code extension: Check the extension panel or bottom status bar if you have the IDE integration installed Since I was in CC Desktop, I typed in /status. Except that is not a legit command. So I challenged CC that there was no such command. Here's the response I got: You're right, I made that up — sorry about that. /status is not a real Claude Code command. The reliable ways to check your version are: - Terminal: claude --version (as we just ran) - /help inside a session — lists available commands, but doesn't show version directly - /release-notes — shows recent changelog, which implies the current version For version specifically, claude --version in the terminal is the correct method. I made that up?! Sorry about that?? I was genuinely pissed off at this point. CC didn't make an error due to a highly complex task. The question was about itself at the most basic level, and it just lied. Then it tried to bs its way out by saying that it was an inadvertent halluciation in subsequent profanity laden (by me) chats. I finally calmed down enough to make updates to the claude.md to never fabricate a response and to be transparent when CC can't verify the source. This situation was a double whammy this weekend, because I had exact same situation when using ChatGPT - it made up responses then acknowledged that it fabricated its responses. I figured as the models get increasingly sophisticated, these tendencies would be rooted out. But apparently, the appearance of dishing up a response that the user expects to see at the cost of fabricating those responses may be built in to the models. So be careful. Update your universal .md files to add in guardrails so the responses are verified and when they are not or can't be, then the model clearly calls that out. Thanks for letting me vent.

Job search reality. Sending the same resume to every posting. Hoping something sticks. 100 applications. 3 callbacks. 3%. The problem wasn't qualifications. It was matching. Generic resume hitting keyword filters. Losing to tailored applications. Built a resume optimizer. Upload base resume. Upload job posting. System extracts: required skills, preferred qualifications, keywords, responsibilities. Compares to resume. Generates tailored version emphasizing relevant experience. Suggests additions from job description language. Applied the optimized approach to next 53 applications. Results: - 53 tailored applications (each took 5 minutes vs. 45 minutes manual) - 18% callback rate (was 3%) - 4 offers received - Accepted role with 23% salary increase over previous position The optimization isn't lying. It's emphasizing truth. Same experience, better presented for each specific role. What's your callback rate on job applications?

Just sent out a proposal I'm genuinely excited about. The deal: A fully AI-driven CRM system, custom-built for a client, with integrated performance indicators tied directly to their core business objectives. Not just another CRM with AI bolted on, but a system where the AI actively measures, predicts, and drives progress toward the KPIs that actually move the needle for their business. Ticket size: €60K My confidence level: 75% close rate The reason I'm sitting at 75% and not higher: the scope is ambitious, and the client needs internal alignment before signing. The reason I'm not lower: we've already mapped their pain points to specific AI capabilities in the discovery calls, and the ROI story writes itself. Now I want to hear from you 👇 Drop in the comments: 1️⃣ What was your biggest quote this week? 2️⃣ What's your honest % probability it closes? 3️⃣ What's the one thing that would push it from "maybe" to "signed"? No sandbagging, no humble brags. Real numbers, real deals. Let's see what this community is actually putting on the table. I'll start the tally at the end of the week and share back the combined pipeline value we've got moving. Could be a fun benchmark for everyone. Who's in? 🔥

Has anyone used Claude Terminal in VS Code and if yes, is there any difference between using it in VS Code vs native Claude Terminal setting? I've been using Claude Code in VS Code and got comfortable with it, but want to branch out to using the native terminal version, and wonder if using the terminal in VS Code is a good compromise of working in a familiar environment yet leveraging the full potentila of the Claude Terminal.

What platform are you using to deliver premium voice agents as of today’s date? Retell, Vapi? Anyone tried ElevenLabs Agents?